3D Object Detection and Tracking Based on Streaming Data
This work addresses the challenge of real-time 3D object detection and tracking for autonomous driving systems, representing an incremental advancement by integrating temporal information into existing deep learning frameworks.
The paper tackled the problem of limited temporal information exploitation in 3D object detection by leveraging streaming data, resulting in significant improvements over frame-by-frame methods and competitive tracking results, such as 76.68% MOTA and 81.65% MOTP on the KITTI benchmark.
Recent approaches for 3D object detection have made tremendous progresses due to the development of deep learning. However, previous researches are mostly based on individual frames, leading to limited exploitation of information between frames. In this paper, we attempt to leverage the temporal information in streaming data and explore 3D streaming based object detection as well as tracking. Toward this goal, we set up a dual-way network for 3D object detection based on keyframes, and then propagate predictions to non-key frames through a motion based interpolation algorithm guided by temporal information. Our framework is not only shown to have significant improvements on object detection compared with frame-by-frame paradigm, but also proven to produce competitive results on KITTI Object Tracking Benchmark, with 76.68% in MOTA and 81.65% in MOTP respectively.